Skip to main content
Glama

DP-MCP Server

by devraj21
verify_ai_config.py3.9 kB
#!/usr/bin/env python3 """ Verify AI configuration is set up correctly. """ import os import subprocess import requests import json def verify_ai_configuration(): """Verify AI configuration status.""" print("🔍 DP-MCP AI Configuration Verification") print("="*50) # 1. Check .env.ai file print("1️⃣ Configuration File Check:") if os.path.exists('.env.ai'): print(" ✅ .env.ai file exists") # Check if placeholder keys are still there with open('.env.ai', 'r') as f: content = f.read() if 'XXXX-REPLACE-WITH-YOUR-ACTUAL' in content: print(" ⚠️ Placeholder API keys detected - replace with real keys for cloud models") else: print(" ✅ API keys appear to be configured") if 'OLLAMA_BASE_URL=http://localhost:11434' in content: print(" ✅ Ollama configuration found") else: print(" ❌ .env.ai file not found") return # 2. Check Ollama print("\n2️⃣ Ollama Service Check:") try: response = requests.get('http://localhost:11434/api/tags', timeout=5) if response.status_code == 200: models = response.json().get('models', []) print(f" ✅ Ollama running with {len(models)} models:") for model in models: size_gb = model['size'] / (1024**3) print(f" • {model['name']}: {size_gb:.1f} GB") else: print(f" ❌ Ollama API error: {response.status_code}") except Exception as e: print(f" ❌ Ollama not accessible: {e}") print(" 💡 Try: ollama serve") # 3. Check MCP Server print("\n3️⃣ MCP Server Check:") try: response = requests.get('http://127.0.0.1:8888/mcp/', timeout=5) print(f" ✅ MCP Server running (HTTP {response.status_code})") except Exception as e: print(f" ❌ MCP Server not accessible: {e}") print(" 💡 Try: uv run python src/dp_mcp/server.py --ai-env production --debug") # 4. Model Size Summary print("\n4️⃣ Model Size Reference:") model_sizes = { 'phi3': '2.2 GB', 'mistral': '4.1 GB', 'llama2': '3.8 GB', 'codellama': '3.8 GB', 'llama2:13b': '7.3 GB' } for model, size in model_sizes.items(): print(f" • {model}: {size}") # 5. Disk Space Check print("\n5️⃣ Disk Space Check:") try: result = subprocess.run(['df', '-h', '/'], capture_output=True, text=True) lines = result.stdout.strip().split('\n') if len(lines) >= 2: header = lines[0] data = lines[1].split() available = data[3] if len(data) > 3 else "Unknown" print(f" Available space: {available}") # Extract numeric value for comparison if 'G' in available: available_gb = float(available.replace('G', '')) if available_gb > 10: print(" ✅ Sufficient space for AI models") else: print(" ⚠️ Low disk space - consider cleanup") except: print(" ❓ Could not check disk space") print("\n🎯 Configuration Summary:") print(" • .env.ai: ✅ Ready") print(" • Local Models: Ready via Ollama") print(" • Cloud Models: Configure API keys to enable") print(" • MCP Server: Ready for AI tools") print("\n🚀 Next Steps:") print(" 1. Replace API key placeholders in .env.ai (optional)") print(" 2. Install more Ollama models: ollama pull mistral") print(" 3. Test AI tools via MCP protocol") print(" 4. Use natural language queries in your applications") if __name__ == "__main__": verify_ai_configuration()

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/devraj21/dp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server